Vellore Institute of Technology (VIT) is a private university located in&nbsp;Tamil Nadu, India. Founded in 1984, as Vellore Engineering College, the institution offers 20 undergraduate, 34 postgraduate, four integrated and four research programs. It has campuses in Vellore, Amravati, Bhopal and Chennai.

VIT is one of the top ranked private universities in India according to NIRF, THE and QS Rankings.&nbsp;Govt. of India has recognized&nbsp;VIT, Vellore as an&nbsp;Institution of Eminence. This has allowed VIT to take independent quality initiatives and move up in world ranking.

&nbsp;

&nbsp;

VIT University

Department of Information Security

Big data is information management system through the integration of various traditional data techniques. Big data usually contains high volume of personal and authenticated information which makes privacy as a major concern. To provide security and effective processing of collected data various techniques are evolved. Machine Learning (ML) is considered as one of the data technology which handles one of the central and hidden parts of collected data. Same like ML algorithm Deep Learning (DL) algorithm learn program automatically from the data it is considered to enhance the performance and security of the collected massive data. This paper reviewed security issues in big data and evaluated the performance of ML and DL in a critical environment. At first, this paper reviewed about the ML and DL algorithm. Next, the study focuses towards issues and challenges of ML and their remedies. Following, the study continues to investigate DL concepts in big data. At last, the study figures out methods adopted in recent research trends and conclude with a future scope.

Department of Digital Communications

School of Information Technology and Engineering

Vellore Campus

School of Computer Science and Engineering

Advances in Human and Social Aspects of Technology

HCI Challenges and Privacy Preservation in Big Data Security

Sensor cloud is the combination of wireless sensor networks and Cloud computing which performs real-time data acquisition and processing in a distributed environment. The infrastructure enables collection, processing, sharing, visualisation, archival and searching of large amounts of sensor data. It makes it possible for sharing computing resources and data, on an unprecedented scale, among an infinite number of geographically distributed groups. The paper provides an implementation of efficient web based technology for processing large, heterogeneous set of data based on Open Geospatial Consortium Standards. The proposed interface uses the sensor cloud middleware and wireless sensors for distributed applications that process large amounts of data. Sensor cloud middleware in the proposed work uses Open Stack and Hadoop framework along with utilities like generic modelling environment, HBase and Zabbix. The user interface with features such as viewing sensor data, scheduling sensors for data collection and alerting users have also been discussed.

Department of Software Systems

Institute for Industry and International Programme

Fulltext

International Journal of Communication Networks and Distributed Systems

Web user interface based on OGC standards for sensor cloud using big data

With the predominance of administration registering and distributed computing, an ever-increasing number of administrations are developing on the internet, producing tremendous volume of information. The mind-boggling administration-created information turn out to be too extensive and complex to be successfully prepared by customary methodologies. The most effective method to store, oversee, and make values from the administration-situated enormous information turn into a vital research issue. With the inexorably huge measure of information, a solitary framework that gives normal usefulness to overseeing and dissecting diverse sorts of administration-produced enormous information is critically required. To address this test, this chapter gives a review of administration-produced huge information and big data-as-a-service. Initially, three sorts of administration-produced huge information are abused to upgrade framework execution. At that point, big data-as-a-service, including big data infrastructure-as-a-Service, big data platform-as-a-service, and big data analytics software-as-a-service, is utilized to give regular huge information-related administrations (e.g., getting to benefit-produced huge information and information investigation results) to clients to improve effectiveness and lessen cost.

VIT Unitversity

Big Data Analytics for Satellite Image Processing and Remote Sensing Advances in Computer and Electrical Engineering

An Analysis of Usage-Induced Big Data

World University root node

Die Unternehmung

Editorial

Cloud is referred to as a collection of infrastructure services, such as Infrastructure as a service (IaaS) and Platform as a service (PaaS), which are made available to us for utilization by various organizations in which the key factor is virtualization of data as it allow the user to manage, handle and compute a large number of tasks very easily. By referring to Cloud technologies we mean runtime such as Hadoop, Dryad and other Map Reduce frameworks. In this paper we would analyse the above mentioned software's and techniques for the cloud system by comparing them on the basis of its processing speed, its data handling capacity, the nature of user friendliness. We would discuss large scale data analysis using different implementations on the above mentioned tools and after that we would give a performance analysis of these tools on the given implementation like Cap3, HEP, Cloudburst. © 2018 The Authors. Published by Elsevier Ltd.

Department of Database Systems

Procedia Computer Science

High Performance Parallel Computing with Cloud Technologies

With the growth of data parallel computing, role of GPU computing in non-graphic applications such as image processing becomes a focus in research fields. Convolution is an integral operation in filtering, smoothing and edge detection. In this article, the process of convolution is realized as a sparse linear system and is solved using Sparse Matrix Vector Multiplication (SpMV). The Compressed Sparse Row (CSR) format of SPMV shows better CPU performance compared to normal convolution. To overcome the stalling of threads for short rows in the GPU implementation of CSR SpMV, a more efficient model is proposed, which uses the Adaptive-Compressed Row Storage (A-CSR) format to implement the same. Using CSR in the convolution process achieves a 1.45x and a 1.159x increase in speed compared to the normal convolution of image smoothing and edge detection operations, respectively. An average speedup of 2.05x is achieved for image smoothing technique and 1.58x for edge detection technique in GPU platform usig adaptive CSR format.

International Journal of Grid and High Performance Computing

GPU Implementation of Image Convolution Using Sparse Model with Efficient Storage Format

Cloud computing is one of the most emerging platforms in the IT industry. It provides shared computer processing resources and other devices on demand. Users can access their resources from anywhere in the world using smartphones. Smartphones users are increasing day by day in the reality. Users cannot use laptop or computers at all the time. However, they can use a smartphone everywhere. To run a simple program in system users needs different compilers for different programming languages. Smartphones do not have enough hardware resources like CPU, memory and much more It is a time-consuming activity to run a small program on smartphones. It also requires much memory to run a program. Some of the programs cannot run on the Android system due to its different architecture from other platforms. So users need a separate application which can execute a program implemented using different programming languages like C, C++, Java and other languages. © IAEME Publication.

Department of Information Technology

Department of Smart Computing

Department of Software and Systems Engineering

International Journal of Civil Engineering and Technology

Online compilers for android using mobile cloud computing

Automatic question generation from text or paragraph is a great challenging task which attracts broad attention in natural language processing. Because of the verbose texts and fragile ranking methods, the quality of top generated questions is poor. In this paper, we present a novel framework Automatic Chinese Question Generation (ACQG) to generate questions from text or paragraph. In ACQG, we use an adopted TextRank to extract key sentences and a template-based method to construct questions from key sentences. Then a multi-feature neural network model is built for ranking to obtain the top questions. The automatic evaluation result reveals that the proposed framework outperforms the state-of-the-art systems in terms of perplexity. In human evaluation, questions generated by ACQG rate a higher score. © 2018, ComSIS Consortium. All rights reserved.

Computer Science and Information Systems

A novel framework for Automatic Chinese Question Generation based on multi-feature neural network model

Precision agriculture (PA) is an interdisciplinary concept of integrating information technology in agriculture to increase the production and quality of the crops. One of the most important and interesting information of technology is Wireless Sensor Network (WSN). This technology is used to collect, monitor and analyse the data from the field of agriculture. This interdisciplinary technology will boost the crop productivity and maintain quality for example, monitoring the pest and disease control, animal tracking and strength of the crop. In this paper, we have surveyed the importance of sensor in PA and the importance of WSN technologies for remote monitoring in the various applications of the agriculture field. © 2017, Springer Science+Business Media, LLC.

Wireless Personal Communications

The Impact of Wireless Sensor Network in the Field of Precision Agriculture: A Review

Smart healthcare is an emergent part in modern telemedical technology. To solve the problem of collecting information from roaming patients, global mobility network (GLOMONET) is a good way for data transferring. It is common sense that wireless circumstance is full of attacks, and the case how to protect the wireless network away from danger attracts researchers. We present a new two-factor authentication scheme for GLOMONETs to vanquish the hazard. Then the formal proof demonstrates that the attacker can crack the session key and the privacy of the scheme with a negligibly higher probability than directly guessing the password. Moreover, according to the informal analysis model, our scheme meets all the security properties. Finally, via performance comparison and network communication simulation by NS-3, our scheme is fit for practicality. © 2018 Elsevier Ltd